Model comparison
Mistral Medium vs Muse Spark 1.2
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 36.3 on the Noometry Index.
Last verified . 21 shared benchmarks.
Mistral AI
MetaSummary
- They share 21 benchmarks with published results for both. Mistral Medium scores higher in 0 categories and Muse Spark 1.2 in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark 1.2 leads 54.1 to 25.0.
- The biggest single-benchmark swing is ProofBench: 9% for Mistral Medium and 43% for Muse Spark 1.2.
- Muse Spark 1.2 is cheaper at $1.25 / $4.25 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium.
- Muse Spark 1.2 accepts more context: 1.05M tokens versus 262K.
- Mistral Medium has downloadable open weights; the other is API-only.
Side by side
| Mistral Medium | Muse Spark 1.2 | |
|---|---|---|
| Provider | Mistral AI | Meta |
| Noometry Index | 36.3 | 50.3 |
| Released | 2023-12-11 | 2026-08-05 |
| Weights | Open | Proprietary |
| Context window | 262K | 1.05M |
| Max output | 262K | 131K |
| Input $ / M tokens | $1.50 | $1.25 |
| Output $ / M tokens | $7.50 | $4.25 |
| Results tracked | 36 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark 1.2 leads
Mistral Medium: 34.2 (#243), Muse Spark 1.2: 49.2 (#51)
| Benchmark | Mistral Medium | Muse Spark 1.2 |
|---|---|---|
| SciCode | 40.2% | 56.4% |
| WeirdML | 43.7% | 60.3% |
| LMArena Coding | 1434 | 1495 |
| DeepSWE | — | 54.9% |
| FrontierCode | 8% | — |
| LMArena WebDev | — | 1533 |
| FrontierSWE | — | 12% |
| ALE-Bench | 763.98 | — |
Agentic & Tool Use Muse Spark 1.2 leads
Mistral Medium: 28.3 (#90), Muse Spark 1.2: 29.4 (#87)
| Benchmark | Mistral Medium | Muse Spark 1.2 |
|---|---|---|
| APEX-Agents | — | 36.4% |
| Berkeley Function Calling Leaderboard | 37.7% | — |
| GDP.pdf | — | 16% |
Reasoning Muse Spark 1.2 leads
Mistral Medium: 24.0 (#167), Muse Spark 1.2: 51.3 (#34)
| Benchmark | Mistral Medium | Muse Spark 1.2 |
|---|---|---|
| CritPt | 0% | 17.7% |
| LMArena Hard Prompts | 1426 | 1486 |
| DTBench | 75.5% | 94.7% |
| LMCA | 26.1% | 48.4% |
| SimpleBench | — | 74.5% |
| Kagi LLM Benchmark | 50% | — |
| NYT Connections (extended) | — | 79.2% |
| Surface Evolver Bench | 26.9% | — |
| Epoch Capabilities Index | — | 154.87 |
Math Muse Spark 1.2 leads
Mistral Medium: 28.1 (#245), Muse Spark 1.2: 46.4 (#70)
| Benchmark | Mistral Medium | Muse Spark 1.2 |
|---|---|---|
| ProofBench | 9% | 43% |
| LMArena Math | 1408 | 1471 |
| OTIS Mock AIME 2024-2025 | 32.2% | — |
| MATH Level 5 | 81.6% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Muse Spark 1.2 leads
Mistral Medium: 25.0 (#265), Muse Spark 1.2: 54.1 (#53)
| Benchmark | Mistral Medium | Muse Spark 1.2 |
|---|---|---|
| LMArena Expert | 1408 | 1480 |
| GPQA Diamond | 59.5% | — |
| Humanity's Last Exam | 4.5% | — |
| SimpleQA Verified | — | 60.3% |
| Vectara Hallucination Rate | 22.7% | — |
Multimodal Muse Spark 1.2 leads
Mistral Medium: 35.3 (#88), Muse Spark 1.2: 43.4 (#25)
| Benchmark | Mistral Medium | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | 1172 | 1305 |
Multilingual Muse Spark 1.2 leads
Mistral Medium: 52.1 (#91), Muse Spark 1.2: 57.1 (#11)
| Benchmark | Mistral Medium | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | 1408 | 1478 |
| LMArena Chinese | 1447 | 1511 |
| LMArena French | 1459 | 1513 |
| LMArena Russian | 1411 | 1487 |
| LMArena Spanish | 1433 | 1498 |
| LMArena German | 1432 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1380 | — |
Instruction Following Muse Spark 1.2 leads
Mistral Medium: 73.7 (#116), Muse Spark 1.2: 76.7 (#36)
| Benchmark | Mistral Medium | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | 1398 | 1461 |
Long Context Muse Spark 1.2 leads
Mistral Medium: 42.9 (#114), Muse Spark 1.2: 45.2 (#48)
| Benchmark | Mistral Medium | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | 1406 | 1475 |
Writing & Preference Muse Spark 1.2 leads
Mistral Medium: 60.0 (#103), Muse Spark 1.2: 72.3 (#14)
| Benchmark | Mistral Medium | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | 1424 | 1482 |
| LMArena Creative Writing | 1391 | 1449 |
| LMArena Multi-Turn | 1418 | 1494 |
| Short-Story Creative Writing | 77.3% | — |
| EQ-Bench Creative Writing | — | 1840 |
Frequently asked questions
Is Mistral Medium better than Muse Spark 1.2?
Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 36.3 on the Noometry Index.
Which is cheaper, Mistral Medium or Muse Spark 1.2?
Muse Spark 1.2 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; Mistral Medium lists at $1.50 and $7.50.
Is Mistral Medium or Muse Spark 1.2 better for coding?
Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Muse Spark 1.2 does, with 1.05M tokens against 262K.
How many benchmarks do Mistral Medium and Muse Spark 1.2 share?
21 benchmarks have published results for both models. Mistral Medium has 36 scored results on Noometry and Muse Spark 1.2 has 31.